Clinical Research Directory

AI-Assisted Bronchoscopy Navigation and Diagnostic System for Severe Pneumonia: A Multicenter Prospective Study

This study will evaluate an embodied-intelligence-assisted bronchoscopy navigation and diagnostic system for patients with severe pneumonia who require clinically indicated bronchoscopy. The system provides real-time visual cues and voice prompts to help physicians localize target lung segments and describe endobronchial findings; physicians remain fully responsible for all clinical decisions. The trial is designed as a prospective, multicenter, controlled study conducted at about ten hospitals in China, with an anticipated sample size of approximately 100 patients. The primary objective is to determine whether AI assistance improves diagnostic agreement compared with the reference assessment, while secondary objectives include navigation success (e.g., loss-of-path rate), procedure time, and complication rates. The results will provide evidence on the safety and effectiveness of AI-assisted bronchoscopy and support product validation and registration.

Ventilator Settings and Outcomes in Pediatric Patients on ECMO for Severe Respiratory Failure

This study aims to describe the effects of ECMO initiation on the intensity of ventilation in the first 24 hours after ECMO initiation and to explore associations between changes in ventilation intensity and hospital mortality in critically ill pediatric patients requiring ECMO for respiratory failure, using the 'Extracorporeal Life Support Organization' (ELSO) registry.

Artificial Intelligence-driven Virtual Standardized Pediatric Patients Trial

Background: China's healthcare system for children faces significant challenges, particularly due to the limited pediatric service capacity of primary healthcare institutions. A shortage of effective and accessible training tools for primary care doctors further hinders progress in addressing this gap. Technological advancements, especially in artificial intelligence, offer a potential solution to improve pediatric care. Artificial intelligence-driven virtual standardized patients (VSPs), leveraging internet and virtual simulation technologies, simulate clinical cases with specific disease characteristics, providing an innovative, efficient, and flexible training method. VSPs are increasingly utilized in medical education, clinical reasoning, and licensure exams. This study focuses on using VSPs to improve the management of common pediatric conditions, which are major health concerns for children and impose significant psychological and financial burdens on families. Methods: This study will involve a three-arm randomized controlled trial to evaluate the effectiveness of a virtual pediatric standardized patient platform in enhancing primary care doctors' management of common pediatric diseases. At least 459 participants, including general practitioners, internal medicine practitioners, surgeons, and pediatricians from more than 10 provinces across China, will be randomly assigned to one of three groups: the virtual patient platform group, the case teaching manual group, or the case teaching video group. Five virtual patient cases covering pneumococcal pneumonia, rotavirus enteritis with hypovolemic shock, hand-foot-and-mouth disease, acute appendicitis, and respiratory failure will be developed, along with corresponding case teaching materials. After a two-week learning period, participants' disease management abilities will be assessed using clinical vignettes. The primary outcome is adherence to best clinical practice guidelines, categorized into full adherence, partial adherence, and nonadherence. Discussion: This study aims to leverage artificial intelligence for capacity enhancement, targeting the shortcomings of primary care pediatrics and using VSP to help enhance primary care pediatrics capacity. It is a randomized controlled trial involving over 300 primary healthcare institutions across more than 10 provinces in China, ensuring broad and representative participation from both developed and underdeveloped regions.